© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 17766
    Prev
    Next
    INDEX
    Explanations

    phrases related to a person's involvement or role in different activities or events

    oai_token-act-pair · gpt-3.5-turbo

    repeated use of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naire
    -0.80
    ibl
    -0.76
    fy
    -0.70
    ulence
    -0.69
    rade
    -0.69
    wich
    -0.68
    iture
    -0.67
    vier
    -0.67
    mate
    -0.67
    ingly
    -0.66
    POSITIVE LOGITS
     midst
    1.02
     process
    0.98
     aftermath
    0.96
     aforementioned
    0.95
     workings
    0.94
     fray
    0.94
     latter
    0.92
     creation
    0.91
     ongoing
    0.90
     direction
    0.90
    Activations Density 0.284%

    No Known Activations